INDEX

Explanations

references to gaming or game mechanics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chodu

-0.15

ãĥ³ãĥĨ

-0.14

Newton

-0.14

.vn

-0.14

 Tencent

-0.14

Ø±ÙģØ©

-0.14

 Fleming

-0.13

uste

-0.13

_DX

-0.13

Ú¯Ø§ÙĨ

-0.13

POSITIVE LOGITS

 mana

0.24

 graveyard

0.23

 creature

0.23

 creatures

0.22

 cards

0.22

 artifact

0.21

 card

0.21

sac

0.20

 decks

0.20

 enchant

0.20

Activations Density 0.016%

references to gaming or game mechanics

No Comments

No Known Activations